Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130323
    Prev
    Next
    INDEX
    Explanations

    birthdays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ле
    -0.08
     workstation
    -0.08
     Eugene
    -0.08
     Grosso
    -0.07
     Tutor
    -0.07
     Cotton
    -0.07
    hola
    -0.07
     Ministerio
    -0.07
    わせ
    -0.07
    .workspace
    -0.07
    POSITIVE LOGITS
    年份
    0.14
     ವರ್ಷ
    0.14
     yearly
    0.13
    Year
    0.13
    _year
    0.13
     birthday
    0.13
     வருட
    0.13
    生日
    0.12
    Years
    0.12
     year
    0.12
    Activations Density 0.014%

    No Known Activations